Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849768fabeff9627892e620fd7ccddc4fcaa46998f6072cf6627608e0eecd774
+oid sha256:efe7552ee4cd7f10a762e15adaa33cf294ac7adcfe2645f279fce53f16a3d8bd
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07bca933ada83901a93f5c56669ea759aed0f96cbc13411fa618cfcf0e1e0581
+oid sha256:45dc63c7144e513e9873aae71b1b0dc54d83846dc8a6d68afda3ecea60350b4b
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4493242d667e51bedb3f5e46756d233639b8c6364f18b2eaf748f1197b64ca2
+oid sha256:f7bde73d548d620adcc91a4d5c375144f9e98941e152fd3a7afcbe0066bb59bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.84165620803833,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0024078979051288226,
+  "best_metric": 2.8120768070220947,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.003611846857693234,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.873,
       "eval_steps_per_second": 7.936,
       "step": 20
+    },
+    {
+      "epoch": 0.002528292800385264,
+      "grad_norm": 1.1254688501358032,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.939,
+      "step": 21
+    },
+    {
+      "epoch": 0.002889477486154587,
+      "grad_norm": 0.9050718545913696,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.7762,
+      "step": 24
+    },
+    {
+      "epoch": 0.003009872381411028,
+      "eval_loss": 2.81711483001709,
+      "eval_runtime": 220.2297,
+      "eval_samples_per_second": 15.883,
+      "eval_steps_per_second": 7.942,
+      "step": 25
+    },
+    {
+      "epoch": 0.0032506621719239105,
+      "grad_norm": 1.16236412525177,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.9007,
+      "step": 27
+    },
+    {
+      "epoch": 0.003611846857693234,
+      "grad_norm": 1.0466458797454834,
+      "learning_rate": 0.0,
+      "loss": 2.4277,
+      "step": 30
+    },
+    {
+      "epoch": 0.003611846857693234,
+      "eval_loss": 2.8120768070220947,
+      "eval_runtime": 220.4209,
+      "eval_samples_per_second": 15.87,
+      "eval_steps_per_second": 7.935,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2115116992561152.0,
+  "total_flos": 3197269872476160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null